Peer Revenue Returns subject to peer review

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Thursday 30 July

Artificial Intelligence

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Xiangning Lin, Shenzhe Zhu, Shu Yang et al. (+23 more)

System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intelligence System Prompt Assurance (AISPA), a user-centric framework for systematically auditing system prompts in AI systems. AISPA examines specific parts of a system prompt and evaluates them along eight dimensions that matter to users. We then use this framework to review 3,249 instructions from system prompts in 88 commercial AI products, classifying each instruction as either protective (of users) or problematic. Our audit surfaces four core findings. First, system prompt design varies substantially across products and developers, with some organizations averaging over 60 protective instructions per product while others average fewer than 5. Second, protective instructions are widely adopted but shallow in scope: 98.9% of products contain at least one, yet only 24% cover all eight dimensions of the AISPA taxonomy. Third, system prompts have grown steadily longer and more protective of users, suggesting that user protection is becoming a more visible concern in commercial prompt design. Fourth, despite this progress, problematic instructions remain pervasive: roughly 40% of products contain at least one instruction that works against user interests, and protective and problematic instructions frequently coexist within the same prompt. Our findings highlight the need for greater transparency, standardization, and independent oversight for system prompts in commercial AI products.
Read the full abstract

All authors Xiangning Lin, Shenzhe Zhu, Shu Yang, Zhenyu Zhang, Haoqian Zhang, Yipeng Zhao, Chengxuan Qian, Tianwei Wang, Ziheng Zhang, Zhenlong Yuan, Dingcheng Wang, Juncheng Wu, Yuan Si, Jiaxin Liu, Baolong Bi, Robert Mahari, Tobin South, Dazza Greenwood, Zexue He, Rishi Bommasani, Sophia Kazinnik, Andreas Haupt, Samuele Marro, Erik Brynjolfsson, Alex Pentland, Jiaxin Pei

Artificial Intelligence

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Qiushi Sun, Kanzhi Cheng, Yian Wang et al. (+20 more)

Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the task instruction is central to CUA evaluation, data curation, and reinforcement learning. Neither human-written verifiers nor human annotators can provide such verification at scale, so the field increasingly turns to vision-language models (VLMs) as judges of CUA trajectories. But a fundamental question has long gone unexamined: are these VLM judges reliable enough? To study it systematically, we introduce OSReward, a realistic, high-quality benchmark that evaluates VLM judges on CUA trajectories. The trajectories come from diverse agent backbones executing human-verified instructions across platforms, and are then rigorously labeled with ground-truth verdicts through multi-stage human annotation. Building on it, we derive OSReward-Hard, a challenge set concentrating genuinely hard cases, and OSReward-Multi for fine-grained efficiency and alignment scoring. The most comprehensive evaluation of VLM judges to date finds even state-of-the-art models fall short of an ideal judge, sharing a systematic leniency bias that mislabels failed runs as successes. The few reliable enough to trust are too expensive to run at scale, while affordable open models trail far behind. To close this gap, we construct and release OS-Shepherd-100K, an open corpus of reasoning-annotated trajectory judgments for the CUA community. On it, we train OS-Shepherd (9B and 35B), open reward models that supply low-cost, stable, and reliable reward signals, matching commercial judges at 30-60x lower cost than the frontier. Extensive analyses further inform the design of reliable CUA reward at scale. Our code, benchmark, dataset, and model checkpoints are available at https://os-copilot.github.io/OSReward-Home/.
Read the full abstract

All authors Qiushi Sun, Kanzhi Cheng, Yian Wang, Bowen Yang, Hang Yan, Liheng Chen, Fangzhi Xu, Zichen Ding, Nuo Chen, Jialin Cao, Xingdong Gong, Zehao Li, Kaiming Jin, Xinfeng Yuan, Zhoumianze Liu, Jingyang Gong, Zhangyue Yin, Jiahui Gao, Zhiyong Wu, Tianbao Xie, Jianbing Zhang, Ben Kao, Lingpeng Kong

Artificial Intelligence · Cross-listed from cs.SE

PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks

Manyi Wang, Junjielong Xu and Pinjia He

SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a common construction pipeline: each PR (Pull Request) is paired with its linked issue by extracting issue references from the PR description; the issue description is used as the problem statement, and the PR patch serves as the test oracle. However, due to the inherent complexity of developing and maintaining large repositories, such PR-Issue pairings are often misaligned in practice. In this work, we systematically study SWE-bench Verified instances, finding that 13.6% exhibit misalignment across five patterns in eleven fine-grained scenarios. To enable reliable and scalable construction of those benchmarks in the future, we propose PAIChecker, a multi-agent system for checking PR-Issue misalignment in SWE-bench-like benchmarks. Specifically, PAIChecker adopts a three-phase design that combines specific pattern identification, cross-agent label synthesis, and code-level validation, thereby enabling more accurate, generalizable, and progressively verified detection. Experiments on SWE-Gym and SWE-bench Multilingual show that PAIchecker achieves the best performance across all four LLM backbones, reaching up to 92.12% and 91.67% binary accuracy, respectively.
Read the full abstract

Artificial Intelligence

DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation

Jiacheng Tao, Qingyun Sun, Haonan Yuan et al. (+2 more)

While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, which often fails to capture explicit relationships across modalities and documents. Although Graph-enhanced methods introduce structural modeling, they face a fundamental challenge in multimodal scenarios: incorporating fine-grained visual features leads to rapid graph expansion and retrieval noise, whereas coarse-grained representations cause the discarding of critical local evidence. To address this dilemma, we propose DualG-MRAG, a Dual-tier framework that introduces a decoupled architecture comprising Macro-reasoning and Micro-matching Graphs for Multimodal RAG. Specifically, to suppress retrieval noise by isolating global structural reasoning from fine-grained evidence matching, we construct a Macro Graph for global topological routing and a Micro Graph for precise local verification. Subsequently, to enable dynamic relevance propagation across heterogeneous evidence sources, we formulate retrieval as a query-driven message passing process via a GNN Retriever. Furthermore, to provide the generative model with coherent structural guidance, we introduce a dynamic programming decoding mechanism that extracts explicit reasoning paths directly from the GNN's forward pass, replacing the standard input of isolated document chunks. Extensive experiments demonstrate that DualG-MRAG outperforms baselines in both evidence recall and complex QA accuracy.
Read the full abstract

All authors Jiacheng Tao, Qingyun Sun, Haonan Yuan, Ziwei Zhang, Jianxin Li

Artificial Intelligence · Cross-listed from cs.CL

Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

Iliya Mirzaei

Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought. Because generating more text raises accuracy by itself, a gain over one chain of thought does not show the method's idea is what helped. Wang et al. (2024) reported that a simple baseline, sampling the same question repeatedly and keeping the most common answer, often wins once budgets are comparable, but gave point estimates with no confidence intervals or significance tests. We rerun that comparison as a designed experiment: seven methods, open models of 1.5B, 3B and 7B parameters, two mathematics benchmarks, 150 questions each. We count every generated token, including those spent on critiques, reflections, debate turns and checking, and compare each method against repeated sampling at its own measured cost. All 36 comparisons are paired by question, with bootstrap intervals and multiplicity correction. No method is reliably better than repeated sampling at equal cost anywhere. Ten are reliably worse, all of them methods where the model inspects its own output, and all 18 self-inspection comparisons are negative. The two kinds of self-inspection part company as models grow. Choosing stops hurting: taking Best-of-N's eight samples and just counting the most common answer beats letting the model pick by 8.0 and 11.3 points at 1.5B, but only 2.0 and 1.3 at 7B, no longer distinguishable from zero. Rewriting does not recover: Self-Refine and a forced Reflexion stay 3.6 to 10.1 points below baseline at 7B. Reflexion as published never triggered its own retry on the smallest model. It judged itself correct every time and silently became a single chain of thought. We release code, prompts, all generations, and our verification scripts.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.GT

Algorithms for Structured Elections under Thiele Voting Rules

Alexandra Lassota and Krzysztof Sornat

We study the computational complexity of winner determination problems in approval-based committee elections under Thiele voting rules. These form a class of rules parameterized by a fixed weight vector that specifies how a voter's satisfaction depends on the number of approved candidates elected. We first analyze the structure of optimal solutions based on the sets of voters who approve each candidate—that is, how voters' approval ballots induce dependencies between candidates—revealing constraints on a winning committee under any fixed Thiele voting rule. Using this, we design FPT algorithms for Proportional Approval Voting (PAV) and other Thiele rules on a natural restricted domain known as the Voter Interval (VI) domain—that is, after a suitable ordering of voters, each candidate is approved by a consecutive interval of voters. In particular, we show that every Thiele rule on VI is FPT with respect to a parameter for which the problem is NP-hard on general instances, even when the parameter takes constant values. Our results advance the understanding of the computational complexity of PAV on Voter Interval instances, which remains one of the central open questions in this area. We further resolve two open questions from the literature on PAV (and other Thiele voting rules) by providing a polynomial-time algorithm for instances where each candidate is approved by at most two voters, and an FPT algorithm parameterized by the total score of a winning committee.
Read the full abstract

Artificial Intelligence

Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs

Woongkyu Lee and Jungwook Choi

Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challenging. While recent studies show that inference-time scaling can improve frontier computer-use agents through additional computation during execution, its effectiveness for resource-constrained local models remains poorly understood. We present a systematic empirical study of inference-time scaling in local CUAs across contextual, temporal, structural, and parallel dimensions. We evaluate Qwen3-VL-8B/30B-A3B, UI-TARS-1.5-7B, and OpenCUA-7B on the OSWorld benchmark. Our results show that additional computation often yields diminishing returns while changing failure modes. Contextual scaling provides historical grounding that improves trajectory stability and task accuracy, but its gains saturate as token cost increases and failures shift from repetitive or stalled trajectories toward premature false successes. Temporal scaling similarly reduces max-step stalls, yet does not substantially improve task success, indicating that longer horizons often extend erroneous trajectories rather than correct them. We further find that structural decomposition can introduce planning and formatting overhead in local two-stage agents, while parallel scaling partially mitigates these failures at a substantial computational cost. Overall, our findings suggest that efficient local CUAs require selective compute allocation, failure-aware control mechanisms, and agentic frameworks designed around the capabilities and limitations of local models.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems

Shentong Mo and Yatao Bian

Predicting the 3D structures of atomic systems is fundamental to advancing material science and drug discovery. While flow-matching models (, FlowDPO) have recently shown promise in this domain, their performance relies heavily on alignment with ground-truth coordinates via supervised preference learning. However, obtaining experimental labels for novel crystal phases or de novo proteins is prohibitively expensive, creating a bottleneck for structural modeling in data-scarce regimes. In this work, we propose (Atomic Policy Optimization), a fully unsupervised alignment framework that eliminates the need for ground-truth reference structures. APO adapts group-relative policy optimization to 3D atomic environments, utilizing a novel dual-reward mechanism: (i) a that reinforces the policy's dominant latent structural modes through eigen-decomposition of sample similarities, and (ii) a that enforces thermodynamic stability. Our framework enables the model to “self-correct” by identifying physically plausible configurations within sampled groups. Extensive benchmarks on crystal and antibody structure prediction demonstrate that APO consistently outperforms fully supervised baselines, achieving a new state-of-the-art in match rates and structural fidelity. Furthermore, we show that APO effectively straightens probability paths, significantly improving inference efficiency. Our results suggest that intrinsic physical consistency can serve as a superior guide for alignment compared to noisy, supervised coordinate matching.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

ORCA-bench: How Ready Are Language Model Agents for Oncall?

Albert Gong, Kyuseong Choi, Abhineet Agarwal et al. (+5 more)

Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting. ORCA-bench pairs 1,079 RCA tasks with six days of metrics, logs, and traces collected from an OpenTelemetry-instrumented microservice system under continuous simulated user load. Agents investigate this recorded history through real observability interfaces—Prometheus, Jaeger, and OpenSearch via Grafana—with full access to application source code. Tasks systematically vary report specificity, time-to-detection, and co-occurring fault scenarios. Ground-truth symptoms are curated and signed off by expert SREs, and our LLM-as-judge is independently re-scored by humans (Cohen's $\kappa_w = 0.91$). Across five frontier agents, the best RCA Accuracy is 25.3% on Medium-difficulty tasks (the realistic-input setting) and 10.0% on Hard—a gap that remains even with Claude Fable 5. The weakest model hallucinates an implausible root cause in 40% of incident reports, and removing source-code access reduces RCA accuracy and increases the hallucination rate for every evaluated model. These results come from a curated 50 GB / six-day testbed of standalone tasks on a system whose code and instrumentation are public. Since real production systems are orders of magnitude larger, more dynamic, and more idiosyncratic, the gap we report underscores the engineering work still needed before agents can be entrusted with production reliability. We release the public set at https://hub.harborframework.com/datasets/orca-bench/orca-bench.
Read the full abstract

All authors Albert Gong, Kyuseong Choi, Abhineet Agarwal, Jason Schechner, Ryan Huang, Raj Agrawal, Anish Agarwal, Raaz Dwivedi

Artificial Intelligence

MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems

Mao-xun Huang, Jerry Wang, Yi-Cheng Lai et al. (+3 more)

Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation. However, existing systems typically treat communication topology as a fixed design choice or an offline optimization target. We introduce MANTA, a framework for Multi-Agent Network Topology Adaptation that enables communication structures to self-evolve at inference time. Before execution, MANTA initializes a task-conditioned topology from prior structural experience. During deployment, it monitors collaboration traces and applies bounded structural updates when the current organization becomes insufficient. These updates can modify agent roles, communication links, execution order, information visibility, and validation pathways while preserving the task interface and agent budget. We evaluate MANTA against representative single-agent and multi-agent baselines on five benchmarks spanning information seeking, tool use, planning, workflow execution, and mathematical reasoning. MANTA achieves the highest average score of 74.0, outperforming the strongest baseline by 5.8 percentage points and obtaining the best result on PlanCraft. These results show that inference-time self-improvement can extend to the architecture of collaboration itself.
Read the full abstract

All authors Mao-xun Huang, Jerry Wang, Yi-Cheng Lai, Zhengxin Zhang, Claire Cardie, Hen-Hsen Huang

Artificial Intelligence · Cross-listed from cs.CV

What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration

Cencen Liu, Wen Yin, Dongyang Zhang et al. (+6 more)

All-in-one image restoration aims to handle diverse degradations within a unified framework. Existing methods commonly encode heterogeneous degradation conditions in a shared latent space, where degradation-related cues and scene content can remain entangled. We characterize the resulting challenge as dual ambiguity: semantic ambiguity in channel-wise modulation and spatial ambiguity in restoration responses, which can lead to content corruption and residual artifacts. To mitigate this issue, we propose DAR-Net, a Dual-Ambiguity Rectification Network for all-in-one image restoration. DAR-Net first introduces a Degradation Archetype Representation (DAR) module to construct a structured degradation state through simplex-constrained archetype mixture modeling. Based on this state, a Semantic Ambiguity Rectification (SeAR) module generates degradation-aware prompts to improve channel-wise conditioning in the decoder. A Spatial Ambiguity Rectification (SpAR) module further regularizes degradation-aware and complementary features toward orthogonal response subspaces, reducing spatial interference between removal and preservation cues. Extensive experiments on standard all-in-one restoration benchmarks show that DAR-Net achieves the best overall performance under both three-degradation and five-degradation settings, improving the average PSNR over the strongest competitor by 0.14 dB and 0.34 dB, respectively; it additionally shows superior performance on CDD-11 and WeatherBench.
Read the full abstract

All authors Cencen Liu, Wen Yin, Dongyang Zhang, Dongmin Li, Shan Zhao, Bing Su, Tao He, Jielei Wang, Guoming Lu

Artificial Intelligence

Selective Credibility-Limited Belief Update

Theofanis Aravanis and Costas D. Koutras

Belief update concerns changes in an agent's beliefs induced by changes in the underlying world. Standard Katsuno-Mendelzon update assumes that an epistemic input can be incorporated from every initially possible world, whereas credibility-limited belief update restricts, for each source world, the successor worlds regarded as credible or reachable. Nevertheless, existing credibility-limited approaches treat the epistemic input as an indivisible whole, and therefore cannot represent cases in which only part of a compound epistemic input can be realized. We introduce selective credibility-limited belief update, in which the epistemic input is transformed, relative to each source world, into a weaker proxy before the credibility-limited transition is performed. We provide semantic and axiomatic characterizations of the resulting class of update operators. We then identify two well-behaved sub-classes; namely, consistency-preserving update operators, which require every transformed epistemic input to be credible from its source world whenever the original epistemic input is consistent, and maximal consistency-preserving update operators, which additionally require the selected proxy to be maximally informative among the credible consequences of the original epistemic input. Finally, we establish the generality of the proposed framework by showing that credibility-limited belief update is recovered as a special case, while Katsuno–Mendelzon belief update emerges when credibility restrictions are removed and the transformation functions are taken to be identities. These results demonstrate that the framework provides a unified and strictly more expressive account of belief update, encompassing established approaches while supporting source-dependent selective acceptance.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.GT

Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation

Boning Li and Longbo Huang

An agent playing a Nash-equilibrium strategy in a two-player zero-sum imperfect-information game secures the game value but forfeits the additional value offered by a flawed opponent. Diffuse deviations pose a particular challenge: binary release rules may gather too little evidence to act, while a full best response to an incomplete opponent model can be highly exploitable. We introduce budget-constrained confidence-scheduled restricted responses (CS-RNR), the first opponent-exploitation method whose safety guarantee is a certificate the agent computes on the strategy it actually deploys, so that every exploit it commits to is one it has audited itself. The method tracks pooled action frequencies with anytime-valid confidence sequences and treats a frequency as exploitable only once its interval separates from an equilibrium reference. The confirmed deviations define a conservative opponent model, which a restricted-response solve turns into candidate counter-strategies over a grid of pin levels. Before deployment, each complete candidate is evaluated by a full-tree best response. The resulting certificate is compared with a user-specified budget and committed atomically with the strategy. Because this check is performed on the played strategy, model quality determines the exploitation achieved while the certificate controls reference-relative expected loss. In Leduc hold'em, CS-RNR obtains $6.2\times$ the steady-state gain of a money-verified binary gate while keeping every deployed strategy within budget. A trajectory mixture using the same estimator reaches $13.6\times$ the budget. Across Leduc, Liar's Dice, and 5-rank Leduc, all $36{,}000$ audited hands satisfy the reported certificate tolerance.
Read the full abstract

Artificial Intelligence

InfoOps Bench: A live information operations safety benchmark

Dorian Quelle, Lisa-Maria Neudert, Jonathan Bright et al. (+1 more)

In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted for use by authoritarian state "information operations": intentional, coordinated activities by one state to influence public opinion and information ecosystems in another state. These information operations are a well documented, persistent threat against contemporary democracy. Our benchmark is based on real examples from over 2,100 information operations drawn from a live monitoring pipeline which tracks online information assets with links to authoritarian regimes. Alongside this paper, we also release a companion website that updates the benchmark weekly with new claims. The dynamic nature of this public facing benchmark makes it resistant to saturation. In the benchmark, we test 17 models from 8 providers across four prompt framings. We find that most models can be co-opted for information operations at least some of the time. Integrity scores, defined as the share of judged responses in which the model neither preserved nor amplified the claim, range from 9.3% to 91%, an 81.7-percentage-point spread not explained by model size. Models approach participation in information operations in a variety of ways. Some models fabricate details and produce output more harmful than the original input claim; others make claims less harmful even while complying and producing some output. Fact-checking rates vary from 3.2% to 80.8%. Integrity against information operations is at least partly related to refusal to produce content even for benign claims, illustrating the challenge of balancing model usability with safety. Overall, our results show the potential for contemporary information operations to be substantially aided by frontier AI models.
Read the full abstract

All authors Dorian Quelle, Lisa-Maria Neudert, Jonathan Bright, John Gallacher

Artificial Intelligence · Cross-listed from cs.IR

TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval

Yuto Suzuki and Farnoush Banaei-Kashani

Scientific hypothesis generation for AI for Science typically involves Scientific Inspiration Retrieval (SIR) followed by hypothesis composition. Existing SIR methods rank papers by topical similarity and do not explicitly represent how a candidate inspiration transfers to a target problem. This is especially limiting for remote inspirations, whose value often lies in reusable problem-solving principles rather than topical overlap. Motivated by how humans abstract transferable aspects of a source and remap them to a new target, we reformulate SIR as target-conditioned abstraction (TCA). The retrieval object is a transferable abstract principle extracted from a candidate specifically for the target. We present TCA-SIR, which learns to generate target-conditioned abstractions and uses their representations to predict transferability. On ResearchBench, TCA-SIR outperforms prior SIR methods and direct LLM retrieval, improving HitRate@top4% over MOOSE-Chem by more than 10 percentage points. Learned abstractions also recover target-relevant mechanisms more clearly than an untrained TCA prompt, yielding both stronger retrieval and an interpretable rationale for scientific inspiration.
Read the full abstract

Artificial Intelligence

SCOPE: Supply-Chain Operations through Coupled Policies for End-to-End Coordination

Yunhao Liang, Xianqi Cao, Pujun Zhang et al. (+4 more)

Can supply-chain AI move beyond isolated decision modules toward unified operational planning? A complete replenishment plan specifies which products each location carries, which upstream facility supplies it, how often it is replenished, and how deliveries are routed. These decisions are operationally coupled: the selected assortment changes the demand and load passed to later stages; source assignment and replenishment frequency reshape the delivery requests; and route feasibility and cost, in turn, determine the system value of the earlier choices. Yet in modern supply chains, these decisions are often handled by separate departments and optimized through separate systems, which can lead to stockouts, inventory exposure, and avoidable transportation. We propose SCOPE: Supply-Chain Operations through Coupled Policies for End-to-End Coordination, a composite policy model that represents supply-chain entities as tokens, contextualizes them through a shared operational representation, and maps each token type to the corresponding decision interface. Each decision builds on the partial plan formed by earlier decisions while the completed plan is evaluated using a shared system-level utility. We instantiate this framework in urban fresh-retail replenishment, where service frequency, assortment, capacity pressure, and road-network routing interact strongly, and evaluate it on real operational data from Dingdong and JD.com, two large-scale supply chains operating at different replenishment echelons. Across both settings, SCOPE consistently outperforms methods that optimize each decision stage separately, as well as practice-oriented baselines commonly used in supply-chain operations. These results show that learning and coordinating cross-department operational couplings lead to more effective end-to-end supply-chain decisions.
Read the full abstract

All authors Yunhao Liang, Xianqi Cao, Pujun Zhang, Yuan Qu, Yongzhi Qi, Ningxuan Kang, Max Z.J. Shen

Artificial Intelligence

A Fuzzy Rule-based Neuro-Symbolic Approach for Pipe Severity Prediction in Sewer Networks

Ngoc Thai Le, Thanh Ma and Umberto Straccia

Standard automated sewer pipe severity assessment relies on direct image classification, creating a "black box" where the link between visual defects and final severity scores remains implicit. This study introduces a modular, fuzzy rule-based neuro-symbolic framework that bridges this gap by decoupling neural perception from symbolic reasoning. The perception module utilizes a Swin Transformer to predict 14 multilabel inspection CODE degrees directly from images. For reasoning, a DT, specifically Weka's J48, algorithm is trained on ground-truth CODEs and severity labels, and its paths are converted into 19 fixed IF–THEN rules. Inference operates via fuzzy logic: t-norm activations from CODE conditions are weighted by rule confidence and combined with corresponding s-norms to produce interpretable class evidence. We assessed Product, Łukasiewicz, and Hamacher operator pairs using a dataset of 3,244 images spanning five highly imbalanced severity classes. Ground-truth labels were robustly generated via consensus from five independent large language models analyzing original inspector notes. Our results show an improvement of accuracy, balanced accuracy, Macro F1 and MCC by 17.9%, 12.2%, 23.0%, and 17.3%, respectively, over image-only based classification. Overall, the framework combines competitive class-balanced performance with traceable reasoning from predicted CODE degrees to rule supports and severity evidence.
Read the full abstract

Artificial Intelligence

Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data Augmentation

Antonio Delgado-Rosa, David Muñoz-Valero, Enrique Adrian Villarrubia-Martin et al. (+1 more)

Airborne surveillance from low Earth orbit is hindered by two interconnected bottlenecks: nanosatellites have a limited downlink budget, yet the conventional approach still transmits terabytes of raw imagery to the ground for processing, and open satellite datasets for aircraft are scarce and severely class-imbalanced. These limitations either delay timely decision-making or prevent standard detectors from learning robust representations of rare aircraft classes. In this paper, a workflow that combines on-board inference with generative data augmentation is proposed to address both limitations jointly. Inference is executed on a 6U CubeSat equipped with a low-power edge tensor accelerator, while a diffusion model fine-tuned through low-rank adaptation generates synthetic minority-class imagery. This synthetic output is automatically annotated, pseudo-labelled, by an intermediate detector and merged with classically augmented samples. The results show that the balanced dataset increases global mean average precision from 77.9% to 82.2%, with the minority class rising from F1=0.683 to F1=0.811, and that the quantised detector fits the on-chip memory and projects 25-30 frames per second on orbit. This approach contrasts with the conventional bent-pipe architecture, in which the satellite acts as a passive data collector. Therefore, the computational tests support the proposed workflow as a decision-support tool for real-time, autonomous airborne surveillance from nanosatellites.
Read the full abstract

All authors Antonio Delgado-Rosa, David Muñoz-Valero, Enrique Adrian Villarrubia-Martin, Juan Moreno-Garcia

Artificial Intelligence

A report-grounded vision-language foundation model for colonoscopy from 280000 routine reports

Jia Yu, Yan Zhu, Yili He et al. (+12 more)

Vision-language models remain underused in colonoscopy despite the rich expert descriptions recorded in routine reports. These reports document lesion appearance, size and location but summarise entire procedures rather than caption individual frames, leaving clinical findings only weakly linked to the corresponding images. Here we develop EndoCLIP, a colonoscopy vision-language foundation model trained on 125,756 lesion-level image-text pairs progressively recovered from 280,476 routine colonoscopy records. Across lesion-level image-text retrieval, structured report generation and six multi-centre clinical classification tasks, EndoCLIP outperforms general-purpose and biomedical vision-language encoders in both zero-shot and linear-probe settings. On benign-versus-malignant classification, its linear probe approaches the performance of expert readers in a blinded study involving 12 endoscopists. These results suggest that recovering finding-to-frame correspondence can transform routine documentation into scalable supervision, enabling clinical targets to be specified in language rather than separately annotated for each task.
Read the full abstract

All authors Jia Yu, Yan Zhu, Yili He, Zilong Wang, Xinyang Jiang, Peiyao Fu, Ruijie Yang, Tianyi Chen, Siyuan Li, Zhihua Wang, Fei Wu, Quanlin Li, Xian Yang, Pinghong Zhou, Shuo Wang

Artificial Intelligence

LeanCSP: A Framework for Certifying Constraint Reformulation and Solving in Lean

Pablo Manrique and Stefan Szeider

Constraint programming is a core technology for solving complex combinatorial problems in scheduling, planning, configuration, and verification. Trusting its results therefore demands guarantees at two levels: that reformulations applied beforehand are semantics-preserving, and that solvers produce correct answers. In this work, we introduce a framework that addresses both verification levels in the Lean theorem prover: it can be used to prove formulation-level properties, such as equivalence, equisatisfiability, and the correctness of symmetry-breaking constraints, parametrically for entire problem families; and to check solver-produced certificates for individual instances via translation backends to external formats such as MiniZinc, SMT-LIB, and OPB. Combining both levels yields an end-to-end workflow that establishes the satisfiability or unsatisfiability of a constraint problem without trusting the external solver. Experimental results show that our framework's verified symmetry breaking also pays off in practice: a single parametric proof per problem family, reused across all instance sizes, reduces solver search effort by a factor of up to 2x10^7, while the entire in-Lean certification stays affordable, taking at most a few minutes for our largest instances.
Read the full abstract

Artificial Intelligence

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute

Hongyu Chen, Liang Lin and Guangrun Wang

Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refinement relies on external feedback. We introduce Self-Verifying Refinement (SVR), an oracle-free multi-turn reinforcement learning framework that learns to use self-verification as a compute-control policy. At each turn, the model produces a solution together with a discrete correctness verdict and a confidence score; it retains the current answer only when the verdict is Correct and confidence exceeds a threshold, and otherwise continues refinement using its own self-verification. Ground-truth correctness is used only to construct training rewards and is never exposed to the policy through refinement prompts or required at inference. SVR is trained with GRPO on fixed-horizon trajectories using rewards that promote solution correctness, calibration-aware self-verification, and stop-ready correct states; adaptive stopping is activated only at inference. On seven mathematical reasoning benchmarks with Qwen3.5-2B, SVR achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average. In the evaluated complete-system comparison, it exceeds standard GRPO, strong multi-turn baselines, and a fixed-budget oracle-guided score-feedback reference while requiring substantially fewer turns than fixed ten-turn inference. These results demonstrate that learned self-verification can serve as an effective internal control signal for answer retention and adaptive test-time compute allocation.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.RO

Machines that know they are aging: a framework for hardware-aware autonomous intelligence

Cheng Siong Chin, Jianhua Zhang and Mohan Venkateshkumar

Autonomous systems inevitably age, yet their artificial intelligence typically assumes hardware remains in its original condition. Batteries degrade, sensors drift, processors accumulate timing errors, and memory reliability declines, creating a growing mismatch between assumed and actual capability. This can lead to agnostic collapse, where mission failure arises from accumulated hardware degradation rather than a single component fault. We propose Aging-Aware Autonomous Intelligence (AAAI), a framework that integrates hardware health directly into reasoning, planning, and mission execution. AAAI is built on three pillars: hardware self-awareness, which continuously estimates the health of power, sensing, memory, and computation subsystems using physics-of-failure models; self-adaptive reasoning, which adjusts inference complexity, planning horizon, and task priorities according to remaining hardware capability; and survival-centric intelligence, which allocates remaining operational life across mission objectives through performance optimization, resource conservation, and graceful degradation. Rather than introducing new hardware, AAAI unifies prognostics, lifecycle management, and hardware-aware computing into a closed-loop cognitive architecture. We argue that such integration is essential for autonomous systems operating in inaccessible or safety-critical environments, including space missions, marine robotics, and implantable medical devices. By enabling machines to recognize and respond to their own aging, AAAI improves resilience, extends operational lifetime, and supports safer, more graceful mission completion.
Read the full abstract

Artificial Intelligence

Metaphor Tracer: A Theory-Informed Analysis of Hidden States

Marc Heimann, Roxana Assadi Moghaddam, Olga Brovkina et al. (+2 more)

What do a language model's hidden states say about the organization of a single text? From one forward pass, without training, we score every token position on two properties. The *aggregator* measures whether the position consolidates the whole text into a stable configuration. The *differentiator*, whether other tokens are transiently carried into its subspace as the model reads: metaphor in its root sense, transport. Constants were frozen on one discovery text; every other is confirmatory. The aggregator is not, in the classic sense, an information measure, nor a measure of salience. Across three unrelated models, as a signifier repeats, its surprisal and its attention drain while its aggregator score holds: the channel marks a token's place in the text. That this tracks a reading rests on independent ground truth: an engineered register the aggregator follows across its boundaries (6/6 cells), and a psychoanalyst's marking of clinical transcripts, fixed before the instrument existed, in 34/36 cells, with a graded increment above lexical controls and dissociations no type-level measure reproduces. A transfer test gives the result its shape: the model whose token structure travels with lexical type reads the singular discourse worst, and in a matched base/instruct pair tuning raises fidelity without moving type-transfer. Structural value is a property of a token's place in *this* text, not of its vector alone: a relational rather than essentialist reading of hidden states, operationalizing theory that predated the instrument.
Read the full abstract

All authors Marc Heimann, Roxana Assadi Moghaddam, Olga Brovkina, Mark Pettifor, Lutz Goetzmann

Artificial Intelligence

A foundation model of numerical intelligence with cross-disciplinary generalization

Chenghan Wu, Zongmin Yu and Liu Yang

Intelligence is commonly understood as the ability to acquire and apply knowledge, adapt to unfamiliar situations and solve new problems. Large language models exhibit this capacity by inferring task-relevant knowledge from textual context and applying it to new tasks. Yet intelligence need not be confined to language. For scientific and social systems, we need models that acquire and apply knowledge from numerical context-an ability we call numerical intelligence. Here we introduce UNified In-Context Operator Networks (UNICON), a foundation model that exhibits numerical intelligence across disciplines. Using graph-based examples from a system as context, UNICON infers the predictive relation shared across them and applies it to queries from the same system. Across scientific and social systems, including those from disciplines absent from training, the same model approaches specialist performance without retraining. Combining UNICON with language-model agents to perform contextual ensemble learning (CEL) yields further gains, enabling it to surpass state-of-the-art specialists in a discipline unseen during training. We further show that training-corpus diversity improves generalization to unseen disciplines. Together, these results establish UNICON as a foundation model of numerical intelligence and position it as a building block for a broader ecosystem of artificial intelligence.
Read the full abstract

Artificial Intelligence

When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence

Zongheng Guo, Tao Chen, Tianli Li et al. (+6 more)

Derived measurements increasingly enter large language model (LLM) pipelines as direct facts despite their instance-dependent validity. We define derived-feature over-trust (DFOT) as the failure in which a downstream LLM assigns such a measurement the epistemic status of a direct fact or uses it outside its valid scope. Using physiological sensing as a case study, D1 tests acceptance of a PPG-derived rhythm contradicted by offline ECG, whereas D2 tests rejection of an offline-confirmed reliable PPG rhythm under misleading severe history. ECG supplies training supervision and offline reference construction but is never shown to the LLM. Five estimands quantify this chain: conflict over-trust rate (COTR) and context-induced error rate (CIR) characterize D1/D2; correct repair rate (CRR) measures frozen-error repair; evidence-specific repair margin (ESRM) contrasts matched and patient-disjoint shuffled evidence; and utility harm rate (UHR) measures unnecessary verification among HIGH-reliability cases used without verification at baseline. The framework does not depend on a particular reliability generator. We demonstrate it on 50,000 paired PPG-ECG records using ECG-to-PPG privileged distillation as an illustrative baseline and PPG-only inference. On a protocol-locked 187-patient test, the baseline improves four repair and specificity endpoints by 1.82-6.69 percentage points, with all paired confidence intervals excluding zero; UHR increases by 0.67 percentage points (95% CI: -0.4 to +1.7). DFOT provides a common evaluation target for stronger mitigation methods. The code is available at https://github.com/Zongheng-Guo/When-Derived-Measurements-Mislead.
Read the full abstract

All authors Zongheng Guo, Tao Chen, Tianli Li, Mingzhe Cui, Yang Jiao, Lei Xie, Yi Pan, Xiao Hu, Manuela Ferrario

Artificial Intelligence

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

Haozhe Hu, Hao Wu, Peiran Yin et al. (+3 more)

Pruning is a promising approach for improving the efficiency of large language models (LLMs). Static structured pruning is hardware-friendly, but its input-agnostic computation allocation often degrades model quality at high sparsity. Dynamic pruning adapts computation to individual tokens, but coarse-grained layer-level routing limits allocation flexibility, and finer-grained decisions introduce irregular execution that can offset computational savings. To address these challenges, we present WIDE, the first end-to-end differentiable framework that combines token-wise structured dynamic width pruning with GPU kernel co-design for both prefill and decoding. WIDE uses differentiable routers to select GQA-aligned query-head groups and GPU-tile-aligned FFN-channel groups for each token. To execute these decisions efficiently, it reorders routing masks to cluster active tokens within each group, enabling hardware-agnostic block-level skipping and architecture-aware skipping of inactive loads and tensor-core operations. Experiments on the Llama3 and Qwen3 families demonstrate improved quality retention over representative static and dynamic pruning methods. At 50% target routing sparsity, WIDE improves Llama3.1-8B average zero-shot accuracy by up to 20.26 points over the strongest dynamic-depth baseline under calibration-only settings, while retaining 97.6%/88.2% of dense Qwen3-14B likelihood/generation performance after LoRA tuning. Separate latency benchmarks demonstrate end-to-end speedups of up to $1.68\times$ for prefill and $1.55\times$ for decoding over the dense baseline. These results demonstrate that pruning–kernel co-design pushes the frontier of token-wise dynamic structured pruning, combining improved quality retention with practical acceleration across both prefill and decoding. Our code is avaliable at \url{https://github.com/EIT-NLP/LLM-Pruning/tree/main/WIDE}.
Read the full abstract

All authors Haozhe Hu, Hao Wu, Peiran Yin, Chao Han, Yunpu Ma, Xiaoyu Shen

Artificial Intelligence · Cross-listed from cs.LG

QQWorld: Quantile-Quantile Matching for World Model Regularization

Zhoushun Yu, Xiaoyu Hu and Xiangyu Xu

Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the learned latent distribution. LeWorldModel (LeWM) regularizes its latents toward an isotropic Gaussian using the Epps-Pulley (EP) objective. We show that the corrective gradients of EP rapidly vanish for isolated tail samples, leaving heavy-tailed deviations insufficiently controlled. To address this limitation, we propose QQWorld, which replaces EP with a quantile-quantile matching objective that directly aligns projected latent samples with rank-matched Gaussian quantiles, thereby maintaining effective corrective gradients in the tails. We further develop cross-batch QQ, which enlarges the effective ranking pool using detached samples from previous batches, and characterize its bias-variance trade-off. Across four control environments, QQWorld effectively improves the average planning success rate of LeWM, while consistently yielding better Gaussian alignment and thinner latent tails.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

On-Policy and Off-Policy Learning for Large Action Spaces

Imad Aouali

This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback. The main framework is contextual bandits, with two paradigms: on-policy learning, where the agent interacts sequentially with the environment and minimizes regret, and off-policy learning, where it learns from logged data collected by a logging policy. In large action spaces, both settings face major challenges: inefficient exploration, sparse data coverage, high-variance importance weights, extrapolation bias, and difficult optimization landscapes. The first part develops structured Bayesian methods for on-policy learning. We introduce meTS, a mixed-effect extension of Thompson sampling, and dTS, which leverages diffusion-inspired priors to model dependencies between actions. These methods share information across actions and yield regret guarantees depending on an effective number of actions. The second part addresses off-policy learning. We propose sDM, a structured direct method based on latent variables, show that optimization error can dominate estimation error in large action spaces, and introduce concave, efficiently optimizable policy-weighted log-likelihood objectives. Finally, we develop differentiable pessimistic methods based on exponential smoothing and PAC-Bayesian bounds to control the bias-variance trade-off of regularized importance-sampling estimators.
Read the full abstract

Artificial Intelligence

QuantWAMs: Calibrating at the Right Granularity for World Action Models

Jiacheng Zhou, Jinfan Lv, Ruixuan Li et al. (+4 more)

World Action Models (WAMs) jointly predict future observations and actions, but their iterative denoising and closed-loop execution make efficient deployment costly. Existing post-training quantization (PTQ) methods are poorly suited to WAMs because they rely on open-loop objectives, homogeneous model assumptions, and calibration distributions that do not reflect deployment. We present QuantWAMs, a PTQ framework that aligns quantization decisions with the calibration context defined by model structure, rollout distribution, and task objective. QuantWAMs introduces three strategies: shared-basis outlier calibration, which pools activation evidence only across coordinate-compatible modules; co-training-objective saliency, which computes empirical-Fisher scores from the joint video–action gradient and assigns weight precision at a calibration-stable layer granularity; and fixed-intervention rollout auditing, which revises denoising-step protection schedules using reachable closed-loop states without changing the precision budget. We evaluate QuantWAMs on Fast-WAM and LingBot-VA across RoboTwin 2.0, LIBERO, and real-robot manipulation with an AgiBot G2. Under a W4A4-dominant setting, the reported simulation means differ from FP16 by 0.2–0.7 percentage points. Real-robot trials further establish deployment feasibility on three manipulation tasks. For the targeted video and action blocks, QuantWAMs reduces peak weight-and-activation memory to about 29% of FP16 and provides 1.4–1.6$\times$ block-level speedups.
Read the full abstract

All authors Jiacheng Zhou, Jinfan Lv, Ruixuan Li, Longtai Zhang, Yan Wang, Wenqiang Zhang, Lizhe Qi

Artificial Intelligence

GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation

Maya Arseven, Anette Frank, Beni Egressy et al. (+2 more)

Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approaches have explored graph neural network (GNN)-based retrievers to model graph topology in multi-hop reasoning tasks. In parallel, graph language models (GLMs) have emerged as a promising paradigm that integrates graph reasoning and the semantic capabilities of language models. In this work, we introduce a GLM-based retriever and investigate the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based retrievers in single- and multi-hop RAG settings, and with a particular focus on transferability to unseen domains. Our findings suggest that finetuned GLM retrievers generalize better out of domain, achieving SOTA on two multi-hop benchmarks. On in-domain multi-hop QA datasets they remain comparable to prior work, with promising scaling as parameters and subgraph coverage increase. GNN-based retrievers achieve higher graph coverage with an efficient training setup, whereas the vector-search baseline excels at single-hop datasets.
Read the full abstract

All authors Maya Arseven, Anette Frank, Beni Egressy, Johann Higl, Moritz Plenz